Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 18469
    Prev
    Next
    INDEX
    Explanations

    information related to infants and young children

    oai_token-act-pair · gpt-3.5-turbo

    references to babies and childbirth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sorcery
    -0.72
     employers
    -0.69
     Merchants
    -0.69
     workplaces
    -0.69
    states
    -0.67
    ablishment
    -0.66
    Auth
    -0.65
     prevailing
    -0.65
    EDIT
    -0.65
    pmwiki
    -0.64
    POSITIVE LOGITS
     puppies
    1.24
     kittens
    1.16
     puppy
    1.11
     toddler
    1.06
     preschool
    1.05
     kitten
    1.04
    Daddy
    1.02
     orphan
    0.99
     autistic
    0.99
     newborn
    0.98
    Activations Density 0.444%

    No Known Activations